This paper proposes a novel training method for the parameters of a type-2 fuzzy neural network (T2FNN) using sliding mode control theory with an adaptive learning rate. The implemented control structure consists of a conventional (PD) controller in parallel with a T2FNN. The former is responsible to guarantee global asymptotic stability in compact space and to form a sliding behavior. The outp...

In this paper, we present an adaptive multi-agent reinforcement learning method for solving congestion control problems on high-speed networks. Traditional reactive congestion control regulates source rate in terms of queue length restricted to a predefined threshold. However, the determination of the congested threshold and sending rate is difficult and inaccurate due to the dynamic nature of ...

Parameter-specific adaptive learning rate methods are computationally efficient ways to reduce the ill-conditioning problems encountered when training large deep networks. Following recent work that strongly suggests that most of the critical points encountered when training such networks are saddle points, we find how considering the presence of negative eigenvalues of the Hessian could help u...

In some practical applications Neural Network (NN), a fast response to external events within extremely short period is required. However, using back propagation (BP) based on gradient descent optimization method obviously not satisfy many applications because of serious problems with BP are slow convergence speed of learning and containment low minima. Over the years, many improvements and mod...

The goal of this paper is to propose novel strategies for adaptive learning of signals defined over graphs, which are observed over a (randomly time-varying) subset of vertices. We recast two classical adaptive algorithms in the graph signal processing framework, namely, the least mean squares (LMS) and the recursive least squares (RLS) adaptive estimation strategies. For both methods, a detail...

This paper investigates optimal structure of Piplined Recurrent Neural Network (PRNN) for adaptive traffic prediction of MPEG video signal via dynamic ATM networks. The traffic signal of each picture type (I, P, and B) of MPEG video is characterized by a nonlinear autoregressive moving average (NARMA) process. Since those modules of PRNN can be performed simultaneously in a pipelined parallelis...

in this paper the author considers a general method, based on time domain samples for spectral manipulation of time limited signals. first, the original signal is divided into some frames in the time domain. then, by presenting a suitable theoretical and computational algorithm, and using a method for improving the speed of convergence, we find the local bandwidth of each frame; thereby, each f...